
#Library for data analysis and processing

import numpy as np
import pandas as pd
import datetime as dt
import seaborn as sns
import regex as re
import matplotlib.pyplot as plt
from matplotlib.cbook import get_sample_data
from matplotlib.offsetbox import (OffsetImage, AnnotationBbox)


import os

#Plotly Library to make graphs
import plotly.io as pio
import plotly.graph_objs as go
from plotly.subplots import make_subplots
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
import plotly.express as px



#Library to be used for reading json file

import json

#Bokeh Library to make graphs
import bokeh
from bokeh.io import output_notebook
from bokeh.plotting import figure, show
from bokeh.models import ColumnDataSource
from bokeh.models.widgets import DataTable, DateFormatter, TableColumn

#Library to display images
from IPython.display import Image

#Use the output_notebook() function to display Bokeh plots in Jupyter notebook
output_notebook()

#Library to ignore warnings
import warnings
warnings.filterwarnings('ignore')


# Importing the Manchester United season's data from wikipedia

man_united_seasons = pd.read_html('https://en.wikipedia.org/wiki/List_of_Manchester_United_F.C._seasons#Seasons', header=0,match='Season')[0]

# Display the dataframe

man_united_seasons.head()


# Making the 1st row as the header as current header is not required

man_united_seasons.columns = man_united_seasons.iloc[0]

# Drop all the columns except Season and Pos and first row

man_united_seasons= man_united_seasons[['Season','Pos']]
man_united_seasons = man_united_seasons.iloc[1: , :]

# Renaming the Pos column to Standing

man_united_seasons.columns = ['Season','Standing']

# Check for duplicates in the dataset

duplicates = man_united_seasons.duplicated().sum()

print(f'Number of duplicates in the dataset are: {duplicates}')

# Identifying the null values

null_values = man_united_seasons.isnull().sum().sum()

print(f'Number of null values in the dataset are: {null_values}')


# Display the dataframe

man_united_seasons.head()

Number of duplicates in the dataset are: 0
Number of null values in the dataset are: 0


# Update Season column with four digits representing the year

pattern2 = '(\d{4})'
man_united_seasons['Season'] = man_united_seasons['Season'].str.extract(pattern2)
man_united_seasons["Season"]= man_united_seasons["Season"].str.split("-", expand = True)

# Update Standings column with values of two digits
# Note: We will consider 2000-2001 season as the year 2001. 

pattern1 = '(\d{1,2})'
man_united_seasons['Standing'] = man_united_seasons['Standing'].str.extract(pattern1)

# Drop nulls if present

man_united_seasons = man_united_seasons.dropna()

# Convert the column values to integer

man_united_seasons['Season'] = man_united_seasons['Season'].astype(int)
man_united_seasons['Standing'] = man_united_seasons['Standing'].astype(int)


# Taking only the data of Manchester United from year 2000-2022 for analysis

man_united_seasons = man_united_seasons.loc[man_united_seasons['Season']>2000]

# Reset Index

man_united_seasons.reset_index(drop=True, inplace=True)


# Display the dataframe

man_united_seasons.head()


def imscatter(x, y, image, ax=None, zoom=1):
    if ax is None:
        ax = plt.gca()
    try:
        image = plt.imread(image)
    except TypeError:
        # Likely already an array...
        pass
    im = OffsetImage(image, zoom=zoom)
    x, y = np.atleast_1d(x, y)
    artists = []
    for x0, y0 in zip(x, y):
        ab = AnnotationBbox(im, (x0, y0), xycoords='data', frameon=False)
        artists.append(ax.add_artist(ab))
    ax.update_datalim(np.column_stack([x, y]))
    ax.autoscale()
    return artists


#Defining the X and Y axis
x = man_united_seasons['Season'].values.astype(int)
y = man_united_seasons['Standing']


#Extracting the crown image and plotting it on the targeted years
image_path = get_sample_data('/Users/prati/Downloads/Crown.png')
fig, ax = plt.subplots(figsize=(15, 4))
imscatter(x[5:8], y[5:8], image_path, zoom=0.1, ax=ax)

#Making the y axis inverted

plt.title('Manchester United Standing in English Premier League')
plt.xlabel('Year')
plt.ylabel('Rank')
plt.ylim(8,0)
plt.xticks(x,rotation = 45)
ax.plot(x, y)
plt.show()


# Load dataset for analysis

premier_league_df = pd.read_csv('Premier_League_data.csv')

# Display output printing first 5 rows

premier_league_df.head()


# Dropping the columns from the dataset

premier_league_df = premier_league_df.drop('Wk', axis=1)

# Check for duplicates in the dataset

duplicates = premier_league_df.duplicated().sum()

print(f'Number of duplicates in the dataset are: {duplicates}')

#identifying the null values

null_values = premier_league_df.isnull().sum().sum()

print(f'Number of null values in the dataset are: {null_values}')

Number of duplicates in the dataset are: 0
Number of null values in the dataset are: 0


percentage = 100

# Filtering Manchester United home games data with no Ronaldo during his first stay

mutd_home_games = premier_league_df[premier_league_df.Home == 'Manchester Utd']

mutd_no_ronaldo = mutd_home_games[(mutd_home_games['Season_End_Year'] < 2003) | (mutd_home_games['Season_End_Year'] > 2009)]

# percentage win in home games
pct_home_wins = ( len(mutd_no_ronaldo[mutd_no_ronaldo['FTR'] == 'H']) / len(mutd_no_ronaldo) ) * percentage
pct_home_wins

# percentage lost in home games
pct_home_loss = ( len(mutd_no_ronaldo[mutd_no_ronaldo['FTR'] == 'A']) / len(mutd_no_ronaldo) ) * percentage
pct_home_loss

# percentage draw in home games
pct_home_draw = ( len(mutd_no_ronaldo[mutd_no_ronaldo['FTR'] == 'D']) / len(mutd_no_ronaldo) ) * percentage
pct_home_draw


# list for pie chart plot

values_unique = ['Win','Lost','Draw']
values_no_ronaldo = [pct_home_wins,pct_home_loss,pct_home_draw]


result = ['Win','Lost','Draw']
percentages_no_ronaldo = [pct_home_wins,pct_home_loss,pct_home_draw]

# Display the output
print(f'Manchester United win percentage at home games: {pct_home_wins:0.2f}%')
print(f'Manchester United lost percentage at home games: {pct_home_loss:0.2f}% ')
print(f'Manchester United draw percentage at home games: {pct_home_draw:0.2f}%')

Manchester United win percentage at home games: 67.95%
Manchester United lost percentage at home games: 12.19% 
Manchester United draw percentage at home games: 19.86%


# Filtering Manchester United home games data with Ronaldo during his first stay
mutd_with_ronaldo = mutd_home_games[(mutd_home_games['Season_End_Year'] >= 2003) & (mutd_home_games['Season_End_Year'] <= 2009)]

# percentage win in home games
pct_home_wins = ( len(mutd_with_ronaldo[mutd_with_ronaldo['FTR'] == 'H']) / len(mutd_with_ronaldo) ) * percentage
pct_home_wins

# percentage lost in home games
pct_home_loss = ( len(mutd_with_ronaldo[mutd_with_ronaldo['FTR'] == 'A']) / len(mutd_with_ronaldo) ) * percentage
pct_home_loss

# percentage draw in home games
pct_home_draw = ( len(mutd_with_ronaldo[mutd_with_ronaldo['FTR'] == 'D']) / len(mutd_with_ronaldo) ) * percentage
pct_home_draw

percentages_with_ronaldo = [pct_home_wins,pct_home_loss,pct_home_draw]


# Display the output
print(f'Manchester United win percentage at home games: {pct_home_wins:0.2f}%')
print(f'Manchester United loss percentage at home games: {pct_home_loss:0.2f}% ')
print(f'Manchester United draw percentage at home games: {pct_home_draw:0.2f}%')

Manchester United win percentage at home games: 75.94%
Manchester United loss percentage at home games: 7.52% 
Manchester United draw percentage at home games: 16.54%


#Generic function to beautify output of print statement
class color:
   BOLD = '\033[1m'


#Plot Donut chart for Home Ground Wins
values = percentages_with_ronaldo
colours = ['#224676', '#B93114', '#04152B']
labels=['Winning %', 'Losing %', 'Tie %']


trace1 = {'values': values, 
          'labels': labels,
          'marker': {'colors': colours},
          'type': 'pie',
          'hole': 0.6,
          'title': '2003-2009',
          'showlegend': True}

print(color.BOLD + '% of Home Ground Wins with Ronaldo Playing for Manchester United (2003 - 2009)')

pio.show({'data': [trace1]})

values1 = percentages_no_ronaldo

trace2 = {'values': values1, 
          'labels': labels,
          'marker': {'colors': colours},
          'type': 'pie',
          'hole': 0.6,
          'title': '1992-2003, 2009<',
          'showlegend': True}

print(color.BOLD + '% of Home Ground Wins without Ronaldo Playing for Manchester United (Before 2003 and after 2009)')
pio.show({'data': [trace2]})

% of Home Ground Wins with Ronaldo Playing for Manchester United (2003 - 2009)

% of Home Ground Wins without Ronaldo Playing for Manchester United (Before 2003 and after 2009)


# Load datasets for analysis

# Creating a dataframe for Ronaldo's career goals

df = pd.read_csv("data.csv")
df_o = pd.read_csv("overall.csv")


# Create a new dataframe with only Club and Year columns

data = df[[ 'Club', 'Year']].value_counts()

season_df = pd.DataFrame(data)
season_df = season_df.reset_index(level=[0,1])

# Add .png to club name for easy parsing while visualizing

season_df['path'] =season_df['Club'] + '.png'


# Check for duplicates in the dataset

duplicates = season_df.duplicated().sum()

print(f'Number of duplicates in the dataframe are: {duplicates}')

#identifying the null values

null_values = season_df.isnull().sum().sum()

print(f'Number of null values in the dataframe are: {null_values}')

# Rename column from 0 to Count

season_df.rename(columns={0:'Count'}, inplace=True)

Number of duplicates in the dataframe are: 0
Number of null values in the dataframe are: 0


# Sort dataframe according to Year

season_df.sort_values("Year", inplace=True)
season_df.head()


# Find all unique values in the columns

pd.DataFrame(df.apply(lambda col: len(col.unique())),columns=["Unique Values Count"])


# generic stats description

df.describe(include=['object']).T


# Method to return image to be displayed on graph

def getImage(path):
    return OffsetImage(plt.imread(path), zoom=.07, alpha = 1)

#Extact year data to be displayed on x-axis

x_axis = season_df['Year'].values

#Display graph

fig, ax = plt.subplots(figsize=(12, 4), dpi=150)
plt.title('Goals per season')
plt.xlabel('Year')
plt.ylabel('Number of Goals')


plt.xticks(x_axis)
ax.scatter(x_axis, season_df['Count'])
ax.plot(x_axis, season_df['Count'])

print('------------------------')
print('Teams Ronaldo Played for')
print('------------------------')

display(Image('Real Madrid.png', width=30))
print('Real Madrid')

display(Image('Manchester United.png', width=30))
print('Manchester United')

display(Image('Sporting CP.png', width=30))
print('Sporting CP')

display(Image('Juventus FC.png', width=30))
print('Juventus FC')

#Iterate through rows and add image to graph

for index, row in season_df.iterrows():
    ab = AnnotationBbox(getImage(row['path']), (row['Year'], row['Count']), frameon=False)
    ax.add_artist(ab)

------------------------
Teams Ronaldo Played for
------------------------

Real Madrid

Manchester United

Sporting CP

Juventus FC


#Read La liga - Spain matches data

json_file = open('Spain_matches.json')
laliga_matches_data = json.load(json_file)


#Assign team id to variable
real_madrid_team_id = '675'

#Get Real madrid teams match data
real_madrid_matches  = [data for data in laliga_matches_data if real_madrid_team_id in data['teamsData'].keys()]


#Store Real madrid team Data in Dataframe
real_madrid_matches_df = pd.DataFrame(real_madrid_matches)

real_madrid_matches_df.head()


#Read Event data from spain_events json file

json_file = open('spain_events.json')
laliga_events_data = json.load(json_file)


#Store Real madrid team Data in Dataframe

laliga_events_df = pd.DataFrame(laliga_events_data)

laliga_events_df.head()


#Get event records for Ronaldo (where Player ID = 3322)

ronaldo_events_data_df = laliga_events_df.loc[laliga_events_df['playerId'] == 3322]


#Method for adding additional columns to distinguish gaol, assists, left foot/right foot goals

def add_columns(tags, tag_id):
    return tag_id in [tag['id'] for tag in tags]


#Distinguish gao and assists - store boolean value

ronaldo_events_data_df['Goal'] = ronaldo_events_data_df['tags'].apply(lambda x: add_columns(x, 101))
ronaldo_events_data_df['Assists'] = ronaldo_events_data_df['tags'].apply(lambda x: add_columns(x, 301))


# Display the output

ronaldo_events_data_df.head()


#Adding match information to the events DataFrame
ronaldo_events_data_df = pd.merge(ronaldo_events_data_df, real_madrid_matches_df, left_on='matchId', right_on='wyId', how="left")


ronaldo_events_data_df.head(2)


#Calculate number of goals scored
goals = [ronaldo_events_data_df['Goal'].sum()]

#Calculate number of assists
assists = [ronaldo_events_data_df['Assists'].sum()]

#Calculate number of shots attempted
shots_attempted = [ronaldo_events_data_df[ronaldo_events_data_df['eventName'] == 'Shot'].count()['eventName']]


statistics = pd.DataFrame([goals, assists, shots_attempted], 
                        columns=['Ronaldo'], 
                        index=['Goal', 'Assists', 'Shots'])

print('-----Ronaldos Goals, Assists Recieved and Shots Attemped-----')
statistics.head()

-----Ronaldos Goals, Assists Recieved and Shots Attemped-----


#Method to draw football pitch
#initializing football pitch variables

width = 700
height = 350
width_pitch = 104
height_pitch = 68
color = 'green'
line_color = 'white'
grey_color = '#808080'
 

def draw_football_pitch():
    
    #Create  Figure for plotting
    pitch = figure(width = width, height = height, toolbar_location="right")
    
    #Draw outline for empty pitch - football ground
    pitch.rect(x=width_pitch/2., y=height_pitch/2., width=width_pitch, height=height_pitch, fill_color=color, line_width=2, line_color=line_color)
    
    #Drawe left penalty area
    pitch.circle(16.5, height_pitch/2., size=50, fill_color=color, line_width=2, line_color=line_color)
    
    #Draw Bigger rectangle
    pitch.rect(x=16.5/2., y=height_pitch/2., width=16.5, height=40.3, fill_color=color, line_width=2, line_color=line_color)
    
    #Draw Smaller rectangle
    pitch.rect(x=5.5/2., y=height_pitch/2., width=5.5, height=18.3, fill_color=color, line_width=2, line_color=line_color)
    
    #Draw Goal post
    pitch.rect(x=0, y=height_pitch/2., width=0.5, height=7.3, fill_color=color, line_width=2, line_color=line_color)
    
    
    #Draw Penalty spot
    pitch.circle(11, height_pitch/2., size=2, fill_color=line_color, line_width=2, line_color=line_color)
    
    #Draw right penalty area
    pitch.circle((width_pitch-16.5), height_pitch/2., size=50, fill_color=color, line_width=2, line_color=line_color)
    
    pitch.rect(x=width_pitch-(16.5/2.), y=height_pitch/2., width=16.5, height=40.3, fill_color=color, line_width=2, line_color=line_color)
    
    #Draw Smaller rectangle
    pitch.rect(x=width_pitch-(5.5/2.), y=height_pitch/2., width=5.5, height=18.3, fill_color=color, line_width=2, line_color=line_color)
    #Draw Goal post
    pitch.rect(x=width_pitch, y=height_pitch/2., width=0.5, height=7.3, fill_color=line_color, line_width=2, line_color=line_color)
    #Draw Penalty spot
    pitch.circle((width_pitch-11), height_pitch/2., size=2, fill_color=line_color, line_width=2, line_color=line_color)
    
    #Draw middle of pitch
    pitch.circle(width_pitch/2.0, y=height_pitch/2.0, size=100, fill_color=color, line_width=2, line_color=line_color)
    pitch.circle(width_pitch/2.0, y=height_pitch/2.0, size=2, fill_color=line_color, line_width=2, line_color=line_color)
    pitch.line([width_pitch/2.0, width_pitch/2.0], [0, height_pitch], line_width=2, line_color=line_color)
    
    return pitch


#Plot positions from where goals were attempted
def plot_position_data(player_data, action_name, color_of_plot):

    x_axis = [(player_data[0]['x']*105)/100. for player_data in player_data]
    y_axis = [(player_data[0]['y']*69)/100. for player_data in player_data]

    pitch = draw_football_pitch()
    pitch.circle(x_axis, y_axis, fill_color=color_of_plot, line_width=1, line_color="blue", fill_alpha=0.2, size=8)
    player_statistics = bokeh.models.Label(x=90, y=280,x_units='screen', y_units='screen', text=str(len(x_axis)) + " " + action_name, text_font_size= '20px', render_mode='css', text_color = 'white')
    pitch.add_layout(player_statistics)

    return pitch


#Extract positions from columns from which goals were shot
ronaldo_goals = ronaldo_events_data_df[ronaldo_events_data_df['Goal'] == True]['positions']


#Extract positions from where shots where attempted
shots_data = ronaldo_events_data_df[ronaldo_events_data_df['eventName'] == 'Shot']
ronaldo_shots = shots_data['positions']


#Plot ronaldo goals
plot_goals = plot_position_data(ronaldo_goals, 'Goals', 'grey')


#Plot shots
plot_shots = plot_position_data(ronaldo_shots, 'Shots', 'grey')


#Generic function to beautify output of print statement
class color:
   BOLD = '\033[1m'


#Visualize shots
print(color.BOLD + 'Positions from which Ronaldo attempted a Goal')
print(color.BOLD + '------------------------------------------')
show(plot_shots)

Positions from which Ronaldo attempted a Goal
------------------------------------------


#Visualize Goals
display(Image('Ronaldo.jpeg', width=100))

print(color.BOLD + 'Positions from which Ronaldo scored a Goal')
print(color.BOLD + '------------------------------------------')
show(plot_goals)

Positions from which Ronaldo scored a Goal
------------------------------------------

	Season	League	League.1	League.2	League.3	League.4	League.5	League.6	League.7	League.8	League.9	FA Cup	EFL Cup	CommunityShield	UEFAFIFA	Top goalscorer(s)[a]	Top goalscorer(s)[a].1
0	Season	Division	Tier	Pld	W	D	L	GF	GA	Pts	Pos	FA Cup	EFL Cup	CommunityShield	UEFAFIFA	Name(s)	Goals
1	1886–87[b]	—	NaN	—	—	—	—	—	—	—	—	R1	NaN	NaN	NaN	Jack Doughty	4
2	1888–89[c]	Combination	NaN	12	8	2	2	27	13	18	—	—	NaN	NaN	NaN	Jack DoughtyRoger Doughty	6
3	1889–90	Alliance	NaN	22	9	2	11	40	45	20	8th	R1	NaN	NaN	NaN	Willie Stewart	10
4	1890–91	Alliance	NaN	22	7	3	12	37	55	17	9th	QR2	NaN	NaN	NaN	Bob Ramsay	7

	Season	Standing
1	1886–87[b]	—
2	1888–89[c]	—
3	1889–90	8th
4	1890–91	9th
5	1891–92	2nd[d]

	Season_End_Year	Wk	Date	Home	HomeGoals	AwayGoals	Away	FTR
0	1993	1	1992-08-15	Coventry City	2	1	Middlesbrough	H
1	1993	1	1992-08-15	Leeds United	2	1	Wimbledon	H
2	1993	1	1992-08-15	Sheffield Utd	2	1	Manchester Utd	H
3	1993	1	1992-08-15	Crystal Palace	3	3	Blackburn	D
4	1993	1	1992-08-15	Arsenal	2	4	Norwich City	A

	Unique Values Count
Season	21
Competition	16
Matchday	52
Year	21
Date	464
Venue	2
Club	4
Opponent	125
Result	51
Playing_Position	6
Minute	106
At_score	35
Type	12
Goal_assist	87

	count	unique	top	freq
Season	701	21	14/15	61
Competition	701	16	LaLiga	311
Matchday	701	52	Group Stage	75
Date	701	464	9/12/15	5
Venue	701	2	H	403
Club	701	4	Real Madrid	450
Opponent	701	125	Sevilla FC	27
Result	701	51	3:00	50
Playing_Position	643	5	LW	356
Minute	701	106	90	17
At_score	701	35	1:00	111
Type	686	11	Right-footed shot	251
Goal_assist	459	86	Karim Benzema	44

	Club	Year	Count	path
19	Sporting CP	2003	5	Sporting CP.png
18	Manchester United	2004	6	Manchester United.png
17	Manchester United	2005	9	Manchester United.png
16	Manchester United	2006	12	Manchester United.png
15	Manchester United	2007	23	Manchester United.png

	status	roundId	gameweek	teamsData	seasonId	dateutc	winner	venue	wyId	label	date	referees	duration	competitionId
0	Played	4406122	38	{'675': {'scoreET': 0, 'coachId': 275283, 'sid...	181144	2018-05-19 18:45:00	0	Estadio de la Cer\u00e1mica	2565927	Villarreal - Real Madrid, 2 - 2	May 19, 2018 at 8:45:00 PM GMT+2	[{'refereeId': 395085, 'role': 'referee'}, {'r...	Regular	795
1	Played	4406122	37	{'692': {'scoreET': 0, 'coachId': 3880, 'side'...	181144	2018-05-12 18:45:00	675	Estadio Santiago Bernab\u00e9u	2565912	Real Madrid - Celta de Vigo, 6 - 0	May 12, 2018 at 8:45:00 PM GMT+2	[{'refereeId': 398923, 'role': 'referee'}, {'r...	Regular	795
2	Played	4406122	34	{'675': {'scoreET': 0, 'coachId': 275283, 'sid...	181144	2018-05-09 19:30:00	680	Estadio Ram\u00f3n S\u00e1nchez Pizju\u00e1n	2565882	Sevilla - Real Madrid, 3 - 2	May 9, 2018 at 9:30:00 PM GMT+2	[{'refereeId': 384946, 'role': 'referee'}, {'r...	Regular	795
3	Played	4406122	36	{'675': {'scoreET': 0, 'coachId': 275283, 'sid...	181144	2018-05-06 18:45:00	0	Camp Nou	2565907	Barcelona - Real Madrid, 2 - 2	May 6, 2018 at 8:45:00 PM GMT+2	[{'refereeId': 378950, 'role': 'referee'}, {'r...	Regular	795
4	Played	4406122	35	{'675': {'scoreET': 0, 'coachId': 275283, 'sid...	181144	2018-04-28 16:30:00	675	Estadio Santiago Bernab\u00e9u	2565891	Real Madrid - Legan\u00e9s, 2 - 1	April 28, 2018 at 6:30:00 PM GMT+2	[{'refereeId': 385473, 'role': 'referee'}, {'r...	Regular	795

	eventId	subEventName	tags	playerId	positions	matchId	eventName	teamId	matchPeriod	eventSec	subEventId	id
0	8	Simple pass	[{'id': 1801}]	3542	[{'y': 61, 'x': 37}, {'y': 50, 'x': 50}]	2565548	Pass	682	1H	2.994582	85	180864419
1	8	Simple pass	[{'id': 1801}]	274435	[{'y': 50, 'x': 50}, {'y': 30, 'x': 45}]	2565548	Pass	682	1H	3.137020	85	180864418
2	8	Simple pass	[{'id': 1801}]	364860	[{'y': 30, 'x': 45}, {'y': 12, 'x': 38}]	2565548	Pass	682	1H	6.709668	85	180864420
3	8	Simple pass	[{'id': 1801}]	3534	[{'y': 12, 'x': 38}, {'y': 69, 'x': 32}]	2565548	Pass	682	1H	8.805497	85	180864421
4	8	Simple pass	[{'id': 1801}]	3695	[{'y': 69, 'x': 32}, {'y': 37, 'x': 31}]	2565548	Pass	682	1H	14.047492	85	180864422

	eventId	subEventName	tags	playerId	positions	matchId	eventName	teamId	matchPeriod	eventSec	subEventId	id	Goal	Assists
76412	1	Ground attacking duel	[{'id': 501}, {'id': 703}, {'id': 1801}]	3322	[{'y': 26, 'x': 96}, {'y': 27, 'x': 91}]	2565596	Duel	675	1H	28.108732	11	189337977	False	False
76414	10	Shot	[{'id': 402}, {'id': 2101}, {'id': 201}, {'id'...	3322	[{'y': 27, 'x': 91}, {'y': 0, 'x': 0}]	2565596	Shot	675	1H	31.052085	100	189337978	False	False
76457	8	Simple pass	[{'id': 1801}]	3322	[{'y': 53, 'x': 68}, {'y': 67, 'x': 53}]	2565596	Pass	675	1H	146.902499	85	189338004	False	False
76589	10	Shot	[{'id': 402}, {'id': 201}, {'id': 1201}, {'id'...	3322	[{'y': 48, 'x': 96}, {'y': 0, 'x': 0}]	2565596	Shot	675	1H	548.744061	100	189338889	False	False
76654	1	Air duel	[{'id': 702}, {'id': 1801}]	3322	[{'y': 84, 'x': 62}, {'y': 81, 'x': 42}]	2565596	Duel	675	1H	713.899672	10	189338224	False	False

The Ronaldo Effect!!!¶

Introduction¶

Objectives¶

As a group of data analysts, we have been hired by the 'World Soccer' sports magazine. Amid the thrilling matches of the FIFA World Cup, the management wants us to release a detailed report on Cristiano Ronaldo using data driven insights to attract and engage the audience.

Datasets and Importing Libraries¶

Datasets¶

Detailed description of the data set(s) and how they were acquired:

1. Premier league matches Dataset

2. Manchester United Club's achievements Dataset

3. Match Events Dataset - Player, Time, Outcome, Position details

4. Ronaldo's Club goals dataset

Project should be graded more heavily on - Data Analysis ¶

Objective I - Manchester United in last 20 years¶

Data Cleaning¶

Drop, Rename, Duplicates and Null Values¶

Formatting Data using Regex¶

Data Visualization¶

Objective II - Home ground winning probability¶

Data Cleaning¶

Drop, Duplicates and Null¶

Note:¶

Home ground Analysis at Manchester United¶

Analysis for Manchester United Without Ronaldo Playing¶

Analysis for Manchester United with Ronaldo Playing¶

Data Visualization¶

Objective III - Cristiano Ronaldo's Career Goals¶

Data Cleaning¶

Drop, Duplicates and Null¶

Sort¶

Cristiano Ronaldo - Team analysis

Data Visualization¶

Interesting Fact¶

Objective IV - Ronaldo Goals Scoring patterns - La liga¶

Data

Tag Information From Dataframe (Assists, Goals)

Data Visualization

Conclusion¶

Objective I¶

This proves that he played a huge role in the club's success.¶

Objective II¶

Objective III¶

Objective IV¶

Recommendation¶

Citations:¶